© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3917
    Prev
    Next
    INDEX
    Explanations

    code blocks indicated with curly brackets

    oai_token-act-pair · gemini-2.0-flash

    rare tokens

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     big
    -0.69
     large
    -0.67
    3
    -0.63
    big
    -0.59
     Large
    -0.58
     more
    -0.57
    large
    -0.54
     "
    -0.54
    ↵
    -0.51
     '
    -0.50
    POSITIVE LOGITS
    ագրություններ
    0.89
    enterOuterAlt
    0.88
     purpoſe
    0.84
    FunctionFlags
    0.83
    UnusedPrivate
    0.81
    MessageOf
    0.81
     ſeveral
    0.79
     myſelf
    0.79
     fubject
    0.79
     ſtate
    0.78
    Activations Density 0.428%

    No Known Activations